Instructions to use typeof/mistral-7b-v0.3-exploded with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use typeof/mistral-7b-v0.3-exploded with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="typeof/mistral-7b-v0.3-exploded")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("typeof/mistral-7b-v0.3-exploded")
model = AutoModelForCausalLM.from_pretrained("typeof/mistral-7b-v0.3-exploded")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use typeof/mistral-7b-v0.3-exploded with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "typeof/mistral-7b-v0.3-exploded"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "typeof/mistral-7b-v0.3-exploded",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/typeof/mistral-7b-v0.3-exploded

SGLang

How to use typeof/mistral-7b-v0.3-exploded with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "typeof/mistral-7b-v0.3-exploded" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "typeof/mistral-7b-v0.3-exploded",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "typeof/mistral-7b-v0.3-exploded" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "typeof/mistral-7b-v0.3-exploded",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use typeof/mistral-7b-v0.3-exploded with Docker Model Runner:
```
docker model run hf.co/typeof/mistral-7b-v0.3-exploded
```

typeof
/

mistral-7b-v0.3-exploded

init

+058e6597d74073e59a1c087ef221d0a7b6bb3889
+41879a9078b17d6b1e91af82be2e4628fd817a4d
+1716595479.8375213

+058e6597d74073e59a1c087ef221d0a7b6bb3889
+e1f1c13fdd20e68f7c6bcc6d6dc9720413defbd7
+1716595479.8412094

+058e6597d74073e59a1c087ef221d0a7b6bb3889
+050e5515d49376fc01e4837d031902c63af98111
+1716595479.8477163

+058e6597d74073e59a1c087ef221d0a7b6bb3889
+980a210e54a39f53a5bbfbf85adc588413cdb90e
+1716595479.8312054

+058e6597d74073e59a1c087ef221d0a7b6bb3889
+4dbb655f8f9c8af4a80974af349d335c8aea12c6
+1716595480.189016

+058e6597d74073e59a1c087ef221d0a7b6bb3889
+37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+1716595480.2595005

+058e6597d74073e59a1c087ef221d0a7b6bb3889
+2fb3ec3cd64834809edb2f77b4402bc63b941def
+1716595479.890154

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@